© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    kiss or kissing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļį
    -0.09
    Bulk
    -0.09
    кол
    -0.08
    åİ»çľĭçľĭ
    -0.08
     пиÑĤаниÑı
    -0.08
    atic
    -0.08
    è§Ĩ线
    -0.08
    yard
    -0.08
    yards
    -0.08
    hee
    -0.08
    POSITIVE LOGITS
    çĹķ
    0.10
    åIJ»
    0.09
    sei
    0.09
    ikal
    0.09
    è¿ĩçļĦ
    0.09
     Pou
    0.09
    ISK
    0.09
    ðŁĴĭ
    0.09
    è¾±
    0.09
    è°ĵ
    0.09
    Activations Density 0.009%

    No Known Activations